rjurney

digraph pig {
	node [label="\N", shape=record];
	graph [bb="0,0,861.06,1532"];
	scope_819 [label="{<f0>1.1 1.2|<f1>GROUP_BY MULTI_QUERY|<f2>job_201204251821_148386}", pos="360,262", rects="263.55,274.4,456.45,299.2 263.55,249.6,456.45,274.4 263.55,224.8,456.45,249.6", width="2.673", height="1.0472"];
	scope_825 [label="{<f0>6.1 6.2 6.3 6.4|<f1>HASH_JOIN MULTI_QUERY|<f2>job_201204251821_148529}", pos="124,150", rects="26.777,162.4,221.22,187.2 26.777,137.6,221.22,162.4 26.777,112.8,221.22,137.6", width="2.6975", height="1.0472"];
	scope_884 [label="{<f0>8.1 8.2 8.3 8.4|<f1>REPLICATED_JOIN GROUP_BY|<f2>job_201204251821_148528}", pos="471,150", rects="362.88,162.4,579.12,187.2 362.88,137.6,579.12,162.4 362.88,112.8,579.12,137.6", width="3.0017", height="1.0472"];
	scope_801 [label="{<f0>2.1 2.2 2.3|<f1>REPLICATED_JOIN MULTI_QUERY MAP_ONLY|<f2>job_201204251821_147833}", pos="266,486", rects="105.2,498.4,426.8,523.2 105.2,473.6,426.8,498.4 105.2,448.8,426.8,473.6", width="4.4555", height="1.0472"];
	scope_815 [lab

rjurney

            // Note: Pig does not have a DateTime type yet, so this is hackery.  
            // See https://issues.apache.org/jira/browse/PIG-1314
            case DataType.CHARARRAY:
                // If it starts like an ISODate...
                if((String)d.startsWith("ISODate(")) {
                    // and it ends like an ISODate...
                    if((String)d.endsWith(")")) {
                       // lets treat it like an ISODate.
                       try {
                           builder.add( field.getName(), new Date((String)d));

rjurney

/* Piggybank */
register /me/pig/contrib/piggybank/java/piggybank.jar

/* Avro */
register /me/pig/build/ivy/lib/Pig/avro-1.5.3.jar
register /me/pig/build/ivy/lib/Pig/json-simple-1.1.jar
register /me/pig/build/ivy/lib/Pig/jackson-core-asl-1.7.3.jar
register /me/pig/build/ivy/lib/Pig/jackson-mapper-asl-1.7.3.jar
register /me/pig/build/ivy/lib/Pig/joda-time-1.6.jar

rjurney

set mapred.job.tracker=local;
set mapred.local.dir=/tmp/hive
set hive.exec.mode.local.auto=false;
set http://fs.default.name=file: ///tmp/hive;

create table from_to (from_address string, to_address string, dt string);

FAILED: Error in metadata: MetaException(message:Got exception: java.net.ConnectException Call to localhost/127.0.0.1:9000 failed on connection exception: java.net.ConnectException: Connection refused)
FAILED: Execution Error, return code 1 from org.apache.hadoop.hive.ql.exec.DDLTask

rjurney

select to_date(dt), count(*) as total from from_to group by to_date(dt) limit 10;

Works ok, but:

select to_date(dt), count(*) as total from from_to group by to_date(dt) order by to_date(dt) limit 10;

FAILED: Error in semantic analysis: Line 1:81 Invalid table alias or column reference dt :(

rjurney

Buildfile: /Users/peyomp/serde/build.xml

compile:
    [javac] /Users/peyomp/serde/build.xml:30: warning: 'includeantruntime' was not set, defaulting to build.sysclasspath=last; set to false for repeatable builds
    [javac] Compiling 1 source file to /Users/peyomp/serde/build/classes
    [javac] /Users/peyomp/serde/src/TimeSeries.java:3: package org.apache.hadoop.hive.ql.exec does not exist
    [javac] import org.apache.hadoop.hive.ql.exec.UDF;
    [javac]                                      ^
    [javac] /Users/peyomp/serde/src/TimeSeries.java:6: cannot find symbol
    [javac] symbol: class UDF

rjurney

# I am making a chart UDF, to convert BigInts from count(6) to ******
# I am trying to find a way to select TimeSeries(count(*)) and group by day, but this results in an error:

select to_date(dt) as total, 
       TimeSeries(CAST(count(*) AS INT)) as stars, 
       count(*) as total 
       from from_to 
       group by to_date(dt)
       order by to_date(dt);

rjurney

#!/opt/local/bin/python

import imaplib
import sys, signal
from avro import schema, datafile, io
import os, re
import email
import inspect, pprint
import getopt
import time

rjurney

import os, sys, time
from flask import Flask, render_template, request, redirect, make_response

PROJECT_ROOT = os.path.dirname(os.path.realpath(__file__)) 
app = Flask(__name__, static_folder=os.path.join(PROJECT_ROOT, 'static'), static_url_path='/static')

rjurney

hadoop@ip-10-4-115-52:~$ bin/hive --service metastore
Starting Hive Metastore Server
org.apache.thrift.transport.TTransportException: Could not create ServerSocket on address 0.0.0.0/0.0.0.0:9083.
	at org.apache.thrift.transport.TServerSocket.<init>(TServerSocket.java:93)
	at org.apache.thrift.transport.TServerSocket.<init>(TServerSocket.java:75)
	at org.apache.hadoop.hive.metastore.TServerSocketKeepAlive.<init>(TServerSocketKeepAlive.java:34)
	at org.apache.hadoop.hive.metastore.HiveMetaStore.startMetaStore(HiveMetaStore.java:3781)
	at org.apache.hadoop.hive.metastore.HiveMetaStore.main(HiveMetaStore.java:3742)
	at sun.reflect.NativeMethodAccessorImpl.invoke0(Native Method)
	at sun.reflect.NativeMethodAccessorImpl.invoke(NativeMethodAccessorImpl.java:39)